Skip to main content
Glama

The Mirror System — AI Citability

by com.danielsdesignstudio

MCP Engine (4th-engine presence)

mcp_engine
Read-only

Measure a brand's presence on the MCP Engine — the 4th engine of brand discovery. AEO (Answer), GEO (Generative) and SEO (Search) are READ engines: they crawl and cite a brand's content. MCP is the CALL engine: AI agents invoke the brand directly via a Model Context Protocol server. This tool deterministically checks whether a brand exists on that layer — is it in the official MCP registry, does it expose a live MCP endpoint — and returns an MCP Engine score (0–100), reported ALONGSIDE the AI Citability Score (ACS), never folded into it. Almost no brand scores above zero yet; that gap is the point. Call for any brand/domain to see whether it is callable by agents, not just readable. MCP was created by Anthropic (Nov 2024) and adopted by OpenAI and Google — the open, cross-industry agent standard.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesBrand website URL (required), e.g. example.com
brandNoBrand name (optional, improves registry matching)

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds behavioral details beyond annotations: it is deterministic, returns a score (0–100) alongside ACS (not folded in), and notes that almost no brands score above zero. Annotations include readOnlyHint and openWorldHint, and description does not contradict them. It provides valuable context for agent behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is informative and front-loaded with the purpose. It is somewhat verbose but every sentence adds value by explaining the MCP concept and the tool's role. Could be slightly tighter but overall well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains the return value (score 0–100 alongside ACS) and the context of MCP being a new standard. However, it does not specify output format or any prerequisites (e.g., auth). Given no output schema, the description covers the essentials but could be more complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description mentions 'brand/domain' but does not add new semantics beyond the schema descriptions for 'url' and 'brand'. It does not explain how the brand parameter improves matching or provide examples.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly defines the tool's purpose: measuring brand presence on MCP Engine, distinct from AEO/GEO/SEO. It explains MCP as the 'CALL engine' and describes what the tool does (deterministically checks registry and live endpoint existence). This differentiates it from sibling tools like 'score' and 'aci55'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states 'Call for any brand/domain to see whether it is callable by agents, not just readable,' providing clear context for when to use. It contrasts with 'read engines' but does not explicitly exclude scenarios or mention alternative tools. However, the usage guidance is clear enough for an agent to decide.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All The Mirror System — AI Citability toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation4/5

Each tool targets a distinct function: benchmark lookup, engine measurement, full audit, record request, quick score, and studio output. Some overlap occurs between 'score' and 'reflect' (both assess citability), but their scope difference (lite vs. full) is clearly delineated in descriptions.

Naming Consistency2/5

Tool names are inconsistent: 'aci55' uses an acronym and number, 'mcp_engine' uses lowercase with underscore, 'reflect' is a single verb, 'request_record' is verb_noun, 'score' is a single noun, and 'studio' is a single noun. No predictable pattern emerges.

Tool Count4/5

With 6 tools, the count is well-scoped for a niche domain like AI citability measurement. Each tool feels justified, covering lookup, scoring, audit, record creation, and output generation.

Completeness4/5

The tool set covers the core lifecycle: quick estimate (score), full audit (reflect), benchmark (aci55), MCP presence check (mcp_engine), record request (request_record), and output generation (studio). Minor gap: no tool for editing or deleting records directly, but that fits the human-approval workflow described.

Resources